Mouse colon analysis

packages <- c("CIMseq", "CIMseq.data", "tidyverse", "circlize", "printr")
purrr::walk(packages, library, character.only = TRUE)
rm(packages)

##DATA
load('../data/CIMseqData.rda')
load('../data/sObj.rda')

#rename classes
renameClasses <- function(class) {
  case_when(
    class == "0" ~ "Stem",
    class == "1" ~ "TA",
    class == "2" ~ "Goblet.Junb",
    class == "3" ~ "Goblet",
    class == "4" ~ "Goblet.Plet1",
    class == "5" ~ "Lgr5+.Mki67",
    class == "6" ~ "Colonocytes",
    class == "7" ~ "Goblet.Mki67",
    class == "8" ~ "Tufft",
    class == "9" ~ "Enteroendocrine",
    TRUE ~ "error"
  )
}

getData(cObjSng, "classification") <- renameClasses(getData(cObjSng, "classification"))
fractions <- getData(sObj, "fractions")
colnames(fractions) <- renameClasses(colnames(fractions))
sObj@fractions <- fractions

Fig 1: classes

plotUnsupervisedClass(cObjSng, cObjMul)

Fig 2: Cell type gene expression

plotUnsupervisedMarkers(
  cObjSng, cObjMul,
  c("Lgr5", "Ptprc", "Chga", "Dclk1", "Slc26a3", "Atoh1"),
  pal = RColorBrewer::brewer.pal(8, "Set1")
)

Fig 3: Cell cycle and architecture marker

plotUnsupervisedMarkers(
  cObjSng, cObjMul, c("Mki67", "Plet1", "Junb"),
  pal = RColorBrewer::brewer.pal(8, "Set1")
)

Fig 4: Connections per multiplet

adj <- adjustFractions(cObjSng, cObjMul, sObj)
table(apply(adj, 1, sum))

0	1	2	3	4	5
45	185	191	53	21	5

Fig 5: Fraction histogram

tibble(fractions = c(fractions)) %>%
  ggplot() +
  geom_histogram(aes(fractions), binwidth = 0.01) +
  theme_bw()

Fig 6: Detected cell types vs. cost

tibble(
  nCellTypes = apply(adj, 1, sum),
  cost = getData(sObj, "costs")
) %>%
  ggplot() +
  geom_boxplot(aes(nCellTypes, cost, group = nCellTypes)) +
  scale_x_continuous(name = "Detected cell types", breaks = 0:max(apply(adj, 1, sum))) +
  theme_bw()

Fig 7: Estimated cell numbers vs. cost

tibble(
  sample = names(getData(sObj, "costs")),
  cost = unname(getData(sObj, "costs"))
) %>%
  inner_join(
    select(estimateCells(cObjSng, cObjMul), sample, estimatedCellNumber), 
    by = "sample"
  ) %>%
  mutate(estimatedCellNumber = round(estimatedCellNumber)) %>%
  ggplot() +
  geom_boxplot(aes(estimatedCellNumber, cost, group = estimatedCellNumber)) +
  scale_x_continuous(
    name = "ERCC estimated cell number", 
    breaks = 0:max(round(pull(estimateCells(cObjSng, cObjMul), estimatedCellNumber)))
  ) +
  theme_bw()

Fig 8: Estimated cell number vs. Detected cell number

ercc <- filter(estimateCells(cObjSng, cObjMul), sampleType == "Multiplet")
nConnections <- apply(adj, 1, sum)
nConnections %>% 
  tibble(
    sample = names(.), 
    detectedConnections = .
  ) %>% 
  inner_join(ercc) %>% 
  mutate(estimatedCellNumber = round(estimatedCellNumber)) %>%
  ggplot() +
  geom_boxplot(aes(estimatedCellNumber, detectedConnections, group = estimatedCellNumber)) +
  scale_x_continuous(
    name = "ERCC estimated cell number", 
    breaks = 0:max(round(ercc$estimatedCellNumber))
  ) +
  scale_y_continuous(
    name = "Detected cell number",
    breaks = 0:max(round(nConnections))
  ) +
  theme_bw()

## Joining, by = "sample"

Fig 9: Detected cell number vs. Total counts

tibble(
  sample = names(nConnections),
  detectedConnections = nConnections
) %>%
  inner_join(tibble(
    sample = colnames(getData(cObjMul, "counts")),
    total.counts = colSums(getData(cObjMul, "counts"))
  ), by = "sample") %>%
  ggplot() +
  geom_boxplot(aes(detectedConnections, total.counts, group = detectedConnections)) +
  scale_x_continuous(
    name = "Detected cell number", 
    breaks = 0:max(nConnections)
  ) +
  scale_y_continuous(name = "Total counts") +
  theme_bw()

Fig 10: Detected cell number vs. Total ERCC counts

tibble(
  sample = names(nConnections),
  detectedConnections = nConnections
) %>%
  inner_join(tibble(
    sample = colnames(getData(cObjMul, "counts")),
    total.ercc = colSums(getData(cObjMul, "counts.ercc"))
  ), by = "sample") %>%
  ggplot() +
  geom_boxplot(aes(detectedConnections, total.ercc, group = detectedConnections)) +
  scale_x_continuous(
    name = "Detected cell number", 
    breaks = 0:max(nConnections)
  ) +
  scale_y_continuous(name = "Total ERCC counts") +
  theme_bw()

Fig 11: Connections

plotSwarmCircos(sObj, cObjSng, cObjMul, classOrder = c(
    "Goblet", "Goblet.Junb", "Goblet.Plet1", "Goblet.Mki67", "Stem",
    "Lgr5+.Mki67", "TA", "Colonocytes", "Tufft", "Enteroendocrine"
))

Fig 12: Filtered

Only detected duplicates and triplicates.
Only ERCC estimated cell number <= 4.
Weight cutoff = 5.

adj <- adjustFractions(cObjSng, cObjMul, sObj, binary = TRUE)
samples <- rownames(adj)
rs <- rowSums(adj)
keep1 <- rs == 2 | rs == 3
keep2 <- samples %in% filter(estimateCells(cObjSng, cObjMul), estimatedCellNumber <= 4)$sample

plotSwarmCircos(
  filterSwarm(sObj, keep1 & keep2), cObjSng, cObjMul, weightCut = 5, 
  classOrder = c(
    "Goblet", "Goblet.Junb", "Goblet.Plet1", "Goblet.Mki67", "Stem",
    "Lgr5+.Mki67", "TA", "Colonocytes", "Tufft", "Enteroendocrine"
))